Analysis of protein database for semantic similarity using map reduce — A survey

Big data analytics is challenging for storage and analysis of large data sets. This paper is to determine the semantic relationships among Gene Ontology (GO) terms which are the attributes of protein database. This is implemented in a prototype system called PROSIM, which is an User interface with protein data collection. Gene ontology term is a collection of GO graph as an attribute in the database. A proposed technique that determine the contexts of terms based on the concept of existence dependency by map reduce in hadoop. Map Reduce is the parallel-processing engine that allows Hadoop to process and store the large data sets in relatively short order. Determining the semantic similarities among GO terms there by analysis and learning the affected proteins was done. The intensity and risk factor was concluded as per the classification.